A study of criteria for grading follicular lymphoma using a cell type classifier from pathology images based on complementary-label learning.

We propose a criterion for grading follicular lymphoma that is consistent with the intuitive evaluation, which is conducted by experienced pathologists. A criterion for grading follicular lymphoma is defined by the World Health Organization (WHO) based on the number of centroblasts and centrocytes within the field of view. However, the WHO criterion is not often used in clinical practice because it is impractical for pathologists to visually identify the cell type of each cell and count the number of centroblasts and centrocytes. Hence, based on the widespread use of digital pathology, we make it practical to identify and count the cell type by using image processing and then construct a criterion for grading based on the number of cells. Here, the problem is that labeling the cell type is not easy even for experienced pathologists. To alleviate this problem, we build a new dataset for cell type classification, which contains the pathologists' confusion records during labeling, and we construct the cell type classifier using complementary-label learning from this dataset. Then we propose a criterion based on the composition ratio of cell types that is consistent with the pathologists' grading. Our experiments demonstrate that the classifier can accurately identify cell types and the proposed criterion is more consistent with the pathologists' grading than the current WHO criterion.

[Dural arteriovenous fistula causing complex visual hallucinations without an anopsia].

We report the case of a 76-year-old woman who presented with recurrent episodes of complex visual hallucinations in her right visual field without an anopsia. The electroencephalogram showed sharp transients in the left parietotemporal region with phase reversals at T5 and P3. FLAIR MRI revealed hyperintense lesions in the left temporo-occipital lobe, located mainly in the left inferior temporal lobe. Cerebral angiography revealed an arteriovenous shunt from the left occipital artery to the left transverse sinus with cortical venous reflux. The complex visual hallucinations were resolved after transarterial embolization. We therefore hypothesize that this patient's complex visual hallucinations were caused by epileptic seizures or changes in cortical blood flow caused by the cortical venous reflux from the arteriovenous fistula. In general, epileptic hallucinations expand into the bilateral visual field. We reveal that in rare cases, complex visual hallucinations can also be limited to the unilateral visual field without an anopsia. Additionally, we reveal that a dural arteriovenous fistula can cause visual hallucinations without hemianopia.