Srinivasan Krishnamurthy

Assessment of symptomatic women for early diagnosis of ovarian cancer: results from the prospective DOvE pilot project

BACKGROUND Around 90% of deaths from ovarian cancer are due to high-grade serous cancer (HGSC), which is frequently diagnosed at an advanced stage. Several cancer organisations made a joint recommendation that all women with specified symptoms of ovarian cancer should be tested with the aim of making an early diagnosis. In the Diagnosing Ovarian Cancer Early (DOvE) study we investigated whether open-access assessment would increase the rate of early-stage diagnosis. METHODS Between May 1, 2008, and April 30, 2011, we enrolled women who were aged 50 years or older and who had symptoms of ovarian cancer. They were offered diagnostic testing with cancer antigen (CA-125) blood test and transvaginal ultrasonography (TVUS) at a central and a satellite open-access centre in Montreal, QC, Canada. We compared demographic characteristics of DOvE patients with those of women in the same age-group in the general population of the area, and compared indicators of disease burden with those in patients with ovarian cancer referred through the usual route to our gynaecological oncology clinic (clinic patients). FINDINGS Among 1455 women assessed, 402 (27·6%) were in the highest-risk age group (≥ 65 years). 239 (16·4%) of 1455 required additional investigations. 22 gynaecological cancers were diagnosed, 11 (50%) of which were invasive ovarian cancers, including nine HGSC. The prevalence of invasive ovarian cancer, therefore, was one per 132 women (0·76%), which is ten times higher than that reported in screening studies. DOvE patients were significantly younger, more educated, and more frequently English speakers than were women in the general population. They also presented with less tumour burden than did the 75 clinic patients (median CA-125 concentration 72 U/mL, 95% CI 12-1190 vs 888 U/mL, 440-1936; p=0·010); Eight (73%) tumours were completely resectable in DOvE patients, compared with 33 (44%) in clinic patients (p=0·075). Seven (78%) of the HGSC in the DOvE group originated outside the ovaries and five were associated with only slightly raised CA-125 concentrations and minimal or no ovarian abnormalities on TVUS. INTERPRETATION The proportion of HGSC that originated outside the ovaries in this study suggests that early diagnosis programmes should aim to identify low-volume disease rather than early-stage disease, and that diagnostic approaches should be modified accordingly. Although testing symptomatic women may result in earlier diagnosis of invasive ovarian cancer, large-scale implementation of this approach is premature. FUNDING Canadian Institutes of Health Research, Montreal General Hospital Foundation, Royal Victoria Hospital Foundation, Cedars Cancer Institute, and La Fondation du Cancer Monique Malenfant-Pinizzotto.

Retrieval and classification of ultrasound images of ovarian cysts combining texture features and histogram moments

This paper presents an effective solution for content-based retrieval and classification of ultrasound medical images representing three types of ovarian cysts: Simple Cyst, Endometrioma, and Teratoma. Our proposed solution comprises of the followings: extraction of low level ultrasound image features combining histogram moments with Gray Level Co-Occurrence Matrix (GLCM) based statistical texture descriptors, image retrieval using a similarity model based on Gowers similarity coefficient which measures the relevance between the query image and the target images, and use of multiclass Support Vector Machine (SVM) for classifying the low level ultrasound image features into their corresponding high level categories. Efficiency of the above solution for ultrasound medical image retrieval and classification has been evaluated using an inprogress database, presently consisting of 478 ultrasound ovarian images. Performance-wise, in retrieval of ultrasound images, our proposed solution has demonstrated above 77% and 75% of average precision considering the first 20 and 40 retrieved results respectively, and an average classification accuracy of 86.90%.

Classification of ultrasound medical images using distance based feature selection and fuzzy-SVM

This paper presents a method of classifying ultrasound medical images towards dealing with two important aspects: (i) optimal feature subset selection for representing ultrasound medical images and (ii) improvement of classification accuracy by avoiding outliers. An objective function combining the concept of between-class distance and within-class divergence among the training dataset has been proposed as the evaluation criteria of feature selection. Searching for the optimal subset of features has been performed using Multi-Objective Genetic Algorithm (MOGA). Applying the proposed criteria, a subset of Grey Level Co-occurrence Matrix (GLCM) and Grey Level Run Length Matrix (GLRLM) based statistical texture descriptors have been identified that maximizes separability among the classes of the training dataset. To avoid the impact of noisy data during classification, Fuzzy Support Vector Machine (FSVM) has been adopted that reduces the effects of outliers by taking into account the level of significance of each training sample. The proposed approach of ultrasound medical image classification has been tested using a database of 679 ultrasound ovarian images and 89.60% average classification accuracy has been achieved.

Local relative GLRLM-based texture feature extraction for classifying ultrasound medical images

This paper presents a new approach of extracting local relative texture feature from ultrasound medical images using the Gray Level Run Length Matrix (GLRLM) based global feature. To adapt the traditional global approach of GLfiLM-based feature extraction method, a three level partitioning of images has been proposed that enables capturing of local features in terms of global image properties. Local relative features are then calculated as the absolute difference of the global features of each lower layer partition sub-block and that of its corresponding upper layer partition block. Performance of the proposed local relative feature extraction method has been verified by applying it in classifying ultrasound medical images of ovarian abnormalities. Besides, significant improvement has been noticed by comparing the proposed method with traditional GLRLM-based feature extraction method in terms of image classification performance.

Content-based retrieval and classification of ultrasound medical images of ovarian cysts

This paper presents a combined method of content-based retrieval and classification of ultrasound medical images representing three types of ovarian cysts: Simple Cyst, Endometrioma, and Teratoma. Combination of histogram moments and Gray Level Co-Occurrence Matrix (GLCM) based statistical texture descriptors has been proposed as the features for retrieving and classifying ultrasound images. To retrieve images, relevance between the query image and the target images has been measured using a similarity model based on Gower’s similarity coefficient. Image classification has been performed applying Fuzzy k-Nearest Neighbour (k-NN) classification technique. A database of 478 ultrasound ovarian images has been used to verify the retrieval and classification accuracy of the proposed system. In retrieving ultrasound images, the proposed method has demonstrated above 79% and 75% of average precision considering the first 20 and 40 retrieved images respectively. Further, 88.12% of average classification accuracy has been achieved in classifying ultrasound images using the proposed method.

Selection of optimal texture descriptors for retrieving ultrasound medical images

Although feature selection has been proven to be very effective in machine learning and pattern classification applications, it has not been widely practiced in the area of image annotation and retrieval. This paper presents a method of selecting a near optimal to optimal subset of statistical texture descriptors in efficient representation and retrieval of ultrasound medical images. An objective function combining the concept of between-class distance and within-class divergence among the training dataset has been proposed as the evaluation criteria of optimality. Searching for the selection of optimal subset of image descriptors has been performed using Multi-Objective Genetic Algorithm (MOGA). The proposed feature selection based approach of image annotation and retrieval has been tested using a database of 679 ultrasound ovarian images and satisfactory retrieval performance has been achieved. Besides, performance of ultrasound medical image retrieval with and without applying feature selection based image annotation technique has also been compared.

Tubo-Ovarian Abscess Caused by Candida Albicans in an Obese Patient

BACKGROUND Tubo-ovarian abscess (TOA) arises in most cases from pelvic infection. Appropriate treatment includes use of antimicrobials and, especially in patients with increased BMI, drainage of the contents. CASE A 44-year-old morbidly obese woman (BMI 72) had a persistent TOA despite receiving antibiotic treatment for four months. She had no history of diabetes, and denied being sexually active. Imaging demonstrated a pelvic abscess of 14.9 × 8.9 × 11.1 cm. Successful percutaneous drainage was performed yielding purulent material which grew Candida albicans. The patient recovered after drainage of the abscess and the addition of fluconazole to her antimicrobials. She had no apparent risk factor for acquiring such an opportunistic infection, other than her morbid obesity. CONCLUSION Because morbid obesity may confer a relative immunodeficiency, morbidly obese patients may develop unusual infections such as opportunistic fungal abscesses.

Non-Hodgkin Lymphomas in Mature Cystic Teratomas: A Case Report and Review of the Literature

BACKGROUND Mature teratomas, better known as dermoid cysts, are the most common ovarian neoplasms in women in the second and third decade of life. They are invariably benign, and most women are asymptomatic. Ovarian cystectomy is the preferred therapeutic option. CASE A 24-year-old woman was planned for elective laparoscopic cystectomy for a suspected teratoma; operative findings led to a unilateral oophorectomy. Pathological analysis of the specimen revealed a focus of large cell lymphoma of unknown lineage arising in a mature cystic teratoma. A total body positron emission tomography (PET) scan revealed no other disease, and the patient was managed conservatively with regular follow-up. CONCLUSION Lymphoma in a teratoma is an excessively rare finding with only five previously reported cases. A review of the literature revealed very different theories as to its pathogenesis and management.