Thomas G. Olsen

Fourteen patients with treatment-resistant cystic and conglobate acne were treated for four months with oral 13-cis-retinoic acid, a synthetic isomer of naturally occurring all-trans-retinoic acid. The average dose was 2.0 mg per kilogram per day. Thirteen patients experienced complete clearing of their disease; the other had 75 per cent improvement, as determined by the number of acne nodules and cysts present before and after therapy. Prolonged remissions, currently lasting as long as 20 months after discontinuation of therapy, have been observed in all 14 patients. Clinical toxicity was limited to the skin and mucous membranes in most patients and was dose dependent and rapidly reversible upon discontinuation of therapy. The mechanism of action of 13-cis-retinoic acid in the therapy of acne probably involves a direct inhibitory effect of the drug on the sebaceous gland.

BACKGROUND: Shrinkage of cutaneous tissue during processing is a source of controversy. This study was designed to prospectively determine tissue shrinkage at two intervals: 1 min after excision and after 24 to 48 h of formalin fixation. Secondarily, gender, age, site, prior biopsy scar and solar elastosis were evaluated with respect to shrinkage. METHODS: Ninety-seven cutaneous specimens were measured prior to excision, 1 min after removal and after 24 to 48 h of formalin fixation. Width of prior biopsy scar, damage to elastic fibers and solar elastosis were subjectively quantified. RESULTS: Significant tissue shrinkage occurred immediately after excision, prior to formalin fixation. Mean shrinkage (95% confidence interval): length 20.66% +/- 2.15% and width 11.79% +/- 2.35%. Range of shrinkage: length 0 to 41.18% and width -18.75% (indicating expansion) to 37.50%. Patient age was significant; shrinkage decreased 0.3% per year of increasing age. Site was less significant; trunk excisions measured 5% greater shrinkage than head/neck excisions. As solar elastosis increased, shrinkage decreased. CONCLUSIONS: Cutaneous tissue shrinkage following excision is primarily because of intrinsic tissue contractility. Increasing patient age and solar elastosis correlate with less shrinkage. The clinicians and dermatopathologists must be cognizant of the expected shrinkage of submitted specimens for settling discrepancies within the medical record.

BACKGROUND: Artificial intelligence is advancing at an accelerated pace into clinical applications, providing opportunities for increased efficiency, improved accuracy, and cost savings through computer-aided diagnostics. Dermatopathology, with emphasis on pattern recognition, offers a unique opportunity for testing deep learning algorithms. AIMS: This study aims to determine the accuracy of deep learning algorithms to diagnose three common dermatopathology diagnoses. METHODS: Whole slide images (WSI) of previously diagnosed nodular basal cell carcinomas (BCCs), dermal nevi, and seborrheic keratoses were annotated for areas of distinct morphology. Unannotated WSIs, consisting of five distractor diagnoses of common neoplastic and inflammatory diagnoses, were included in each training set. A proprietary fully convolutional neural network was developed to train algorithms to classify test images as positive or negative relative to ground truth diagnosis. RESULTS: Artificial intelligence system accurately classified 123/124 (99.45%) BCCs (nodular), 113/114 (99.4%) dermal nevi, and 123/123 (100%) seborrheic keratoses. CONCLUSIONS: Artificial intelligence using deep learning algorithms is a potential adjunct to diagnosis and may result in improved workflow efficiencies for dermatopathologists and laboratories.