Christof A. Bertram

The Pathologist 2.0: An Update on Digital Pathology in Veterinary Medicine

Using light microscopy to describe the microarchitecture of normal and diseased tissues has changed very little since the middle of the 19th century. While the premise of histologic analysis remains intact, our relationship with the microscope is changing dramatically. Digital pathology offers new forms of visualization, and delivery of images is facilitated in unprecedented ways. This new technology can untether us entirely from our light microscopes, with many pathologists already performing their jobs using virtual microscopy. Several veterinary colleges have integrated virtual microscopy in their curriculum, and some diagnostic histopathology labs are switching to virtual microscopy as their main tool for the assessment of histologic specimens. Considering recent technical advancements of slide scanner and viewing software, digital pathology should now be considered a serious alternative to traditional light microscopy. This review therefore intends to give an overview of the current digital pathology technologies and their potential in all fields of veterinary pathology (ie, research, diagnostic service, and education). A future integration of digital pathology in the veterinary pathologist’s workflow seems to be inevitable, and therefore it is proposed that trainees should be taught in digital pathology to keep up with the unavoidable digitization of the profession.

Validation of Digital Microscopy Compared With Light Microscopy for the Diagnosis of Canine Cutaneous Tumors

Integration of new technologies, such as digital microscopy, into a highly standardized laboratory routine requires the validation of its performance in terms of reliability, specificity, and sensitivity. However, a validation study of digital microscopy is currently lacking in veterinary pathology. The aim of the current study was to validate the usability of digital microscopy in terms of diagnostic accuracy, speed, and confidence for diagnosing and differentiating common canine cutaneous tumor types and to compare it to classical light microscopy. Therefore, 80 histologic sections including 17 different skin tumor types were examined twice as glass slides and twice as digital whole-slide images by 6 pathologists with different levels of experience at 4 time points. Comparison of both methods found digital microscopy to be noninferior for differentiating individual tumor types within the category epithelial and mesenchymal tumors, but diagnostic concordance was slightly lower for differentiating individual round cell tumor types by digital microscopy. In addition, digital microscopy was associated with significantly shorter diagnostic time, but diagnostic confidence was lower and technical quality was considered inferior for whole-slide images compared with glass slides. Of note, diagnostic performance for whole-slide images scanned at 200× magnification was noninferior in diagnostic performance for slides scanned at 400×. In conclusion, digital microscopy differs only minimally from light microscopy in few aspects of diagnostic performance and overall appears adequate for the diagnosis of individual canine cutaneous tumors with minor limitations for differentiating individual round cell tumor types and grading of mast cell tumors.

A Guided Spatial Transformer Network for Histology Cell Differentiation

Identification and counting of cells and mitotic figures is a standard task in diagnostic histopathology. Due to the large overall cell count on histological slides and the potential sparse prevalence of some relevant cell types or mitotic figures, retrieving annotation data for sufficient statistics is a tedious task and prone to a significant error in assessment. Automatic classification and segmentation is a classic task in digital pathology, yet it is not solved to a sufficient degree. We present a novel approach for cell and mitotic figure classification, based on a deep convolutional network with an incorporated Spatial Transformer Network. The network was trained on a novel data set with ten thousand mitotic figures, about ten times more than previous data sets. The algorithm is able to derive the cell class (mitotic tumor cells, non-mitotic tumor cells and granulocytes) and their position within an image. The mean accuracy of the algorithm in a five-fold cross-validation is 91.45%. In our view, the approach is a promising step into the direction of a more objective and accurate, semi-automatized mitosis counting supporting the pathologist.

Ovarian lesions in 44 rabbits (Oryctolagus cuniculus)

The clinical and pathological records of 44 domestic, female rabbits with an age ranging from 6–124 months (median age: 63.5 month) were assessed retrospectively for ovarian lesions. Included were all rabbits that underwent an ovariohysterectomy with a subsequent pathological examination of the genital tract between March 1997 and June 2016. Pathological examination revealed ovarian lesions in 12 of the 44 rabbits including follicular cysts (n=7), cystic rete ovarii (n=3), widespread ovarian necrosis with dystrophic calcification (n=2), ovarian adenoma (n=1). Clinical examination including radiographs only suggested ovarian disorders in two cases of ovarian necrosis with dystrophic calcification and in two cases of cystic rete ovarii. Clinical significance was only conclusive in a case of cystic rete ovarii.

Pseudodiverticula of the Small Intestine Associated With Idiopathic Smooth Muscle Hypertrophy in Domestic Rabbits (Oryctolagus cuniculus)

Acquired outpouches of the intestinal tract are referred to as pseudodiverticula or false pulsion diverticula. In contrast to true diverticula, in which the wall contains all layers of the intestinal tract, the wall of pseudodiverticula lacks the tunica muscularis. Smooth muscle hypertrophy of the small intestine is commonly considered a cause of pseudodiverticulosis in animals due to increased intraluminal pressure. This study reports pseudodiverticula associated with idiopathic smooth muscle hypertrophy of the small intestine in lagomorphs. Four domestic rabbits had single or multiple (up to 200) pseudodiverticula of various size in the small intestine. In all cases the tunica muscularis was diffusely thickened, significantly exceeding reference thickness of 14 rabbits (mean, 112.3 µm; range, 26.3–389.0 µm). Clinical signs were considered to be caused by severe necrosis and inflammation of the wall of large pseudodiverticula, leading to perforation with subsequent peritonitis and mesenteric and omental abscess formation in 2 cases.

Genital Tract Pathology in Female Pet Guinea Pigs (Cavia porcellus): a Retrospective Study of 655 Post-mortem and 64 Biopsy Cases

Disorders of the female genital tract are among the most common disorders in pet guinea pigs (Cavia porcellus); however, knowledge of many aspects of these disorders is sparse, especially regarding their incidence and age distribution. Ovarian cysts, as the most common genital tract disorder in guinea pigs, have been investigated in detail; however, information on the nature of these cysts is inconsistent. The present study reviewed genital tract disorders occurring within 655 full post-mortem examinations of intact female pet guinea pigs and 64 female genital tract biopsies examined over a 22.5 year period. Age distribution was determined from 550 post-mortem examinations of animals of known age. Genital tract disorders were found in 295 post-mortem examinations (45.0%) in animals with a median age of 52 months. Additionally, disorders were found in all genital tract biopsy samples from guinea pigs with a median age of 48 months. The incidence of genital tract diseases increased from 1.5% in guinea pigs ≤6 months of age to up to 77.8% in animals >6 years of age. Ovarian cysts were the most common genital tract disorder, found in 245 of the 655 post-mortem cases (37.4%) and 38 of 43 ovarian biopsy samples (88.4%). The incidence of ovarian cysts increased with advancing age, reaching 75.6% in animals >6 years. In 119 cases, histopathology and immunohistochemistry confirmed cystic rete ovarii as the only cyst type. A Fallopian tube adenoma was found in a single case, so disorders of the Fallopian tube should be considered rare. Uterine disorders were diagnosed in 17.4% of the post-mortem examinations and 98.1% of uterine biopsy samples. Uterine neoplasia, hyperplasia and inflammation were common, but occurred at different ages. The incidence of uterine neoplasia and hyperplasia was higher in older animals (>15% in guinea pigs >6 years), while the incidence of uterine inflammation was the highest (17.9%) in animals aged 7-12 months. An association between ovarian cysts and uterine neoplasia or hyperplasia was not evident. Vaginal disorders were rare and included leiomyoma, polyps and vaginitis.

Classification of Mitotic Cells

Tumor diagnostics are based on histopathological assessments of tissue biopsies of the suspected carcinogen region. One standard task in histopathology is counting of mitotic cells, a task that provides great potential to be improved in speed, accuracy and reproducability. The advent of deep learning methods brought a significant increase in precision of algorithmic detection methods, yet it is dependent on the availability of large amounts of data, completely capturing the natural variability in the material. Fully segmented images are provided by the MITOS dataset with 300 mitotic events. The ICPR2012 dataset provides 326 mitotic cells and in AMIDA2014 dataset, 550 mitotic cells for training and 533 for testing. In contrast to these datasets, a dataset with high number of mitotic events is missing. For this, either one of two pathologist annotated at least 10 thousand cell images for cells of the type mitosis, eosinophilic granulocyte and normal tumor cell from canine mast cell tumor whole-slide images, exceeding all publicly available data sets by approximately one order of magnitude. We tested performance using a standard CNN approach and found accuracies of up to 0.93.