Machine learning can reliably predict malignancy of breast lesions based on clinical and ultrasonographic features.

PURPOSE: To establish a reliable machine learning model to predict malignancy in breast lesions identified by ultrasound (US) and optimize the negative predictive value to minimize unnecessary biopsies. METHODS: We included clinical and ultrasonographic attributes from 1526 breast lesions classified as BI-RADS 3, 4a, 4b, 4c, 5, and 6 that underwent US-guided breast biopsy in four institutions. We selected the most informative attributes to train nine machine learning models, ensemble models and models with tuned threshold to make inferences about the diagnosis of BI-RADS 4a and 4b lesions (validation dataset). We tested the performance of the final model with 403 new suspicious lesions. RESULTS: The most informative attributes were shape, margin, orientation and size of the lesions, the resistance index of the internal vessel, the age of the patient and the presence of a palpable lump. The highest mean negative predictive value (NPV) was achieved with the K-Nearest Neighbors algorithm (97.9%). Making ensembles did not improve the performance. Tuning the threshold did improve the performance of the models and we chose the algorithm XGBoost with the tuned threshold as the final one. The tested performance of the final model was: NPV 98.1%, false negative 1.9%, positive predictive value 77.1%, false positive 22.9%. Applying this final model, we would have missed 2 of the 231 malignant lesions of the test dataset (0.8%). CONCLUSION: Machine learning can help physicians predict malignancy in suspicious breast lesions identified by the US. Our final model would be able to avoid 60.4% of the biopsies in benign lesions missing less than 1% of the cancer cases.

IOeRT conventional and FLASH treatment planning system implementation exploiting fast GPU Monte Carlo: The case of breast cancer.

Partial breast irradiation for the treatment of early-stage breast cancer patients can be performed by means of Intra Operative electron Radiation Therapy (IOeRT). One of the main limitations of this technique is the absence of a treatment planning system (TPS) that could greatly help in ensuring a proper coverage of the target volume during irradiation. An IOeRT TPS has been developed using a fast Monte Carlo (MC) and an ultrasound imaging system to provide the best irradiation strategy (electron beam energy, applicator position and bevel angle) and to facilitate the optimisation of dose prescription and delivery to the target volume while maximising the organs at risk sparing. The study has been performed in silico, exploiting MC simulations of a breast cancer treatment. Ultrasound-based input has been used to compute the absorbed dose maps in different irradiation strategies and a quantitative comparison between the different options was carried out using Dose Volume Histograms. The system was capable of exploring different beam energies and applicator positions in few minutes, identifying the best strategy with an overall computation time that was found to be completely compatible with clinical implementation. The systematic uncertainty related to tissue deformation during treatment delivery with respect to imaging acquisition was taken into account. The potential and feasibility of a GPU based full MC TPS implementation of IOeRT breast cancer treatments has been demonstrated in-silico. This long awaited tool will greatly improve the treatment safety and efficacy, overcoming the limits identified within the clinical trials carried out so far.

COVID-19 therapy optimization by AI-driven biomechanical simulations.

The COVID-19 disease causes pneumonia in many patients that in the most serious cases evolves into the Acute Distress Respiratory Syndrome (ARDS), requiring assisted ventilation and intensive care. In this context, identification of patients at high risk of developing ARDS is a key point for early clinical management, better clinical outcome and optimization in using the limited resources available in the intensive care units. We propose an AI-based prognostic system that makes predictions of oxygen exchange with arterial blood by using as input lung Computed Tomography (CT), the air flux in lungs obtained from biomechanical simulations and Arterial Blood Gas (ABG) analysis. We developed and investigated the feasibility of this system on a small clinical database of proven COVID-19 cases where the initial CT and various ABG reports were available for each patient. We studied the time evolution of the ABG parameters and found correlation with the morphological information extracted from CT scans and disease outcome. Promising results of a preliminary version of the prognostic algorithm are presented. The ability to predict the evolution of patients' respiratory efficiency would be of crucial importance for disease management.

Suspected contact scrotal dermatitis in the dog: a retrospective study of 13 cases (1987 to 2003).

OBJECTIVES: The aim of this study was to assess the clinical and aetiological aspects of contact dermatitis of the scrotum in dogs. METHODS: The medical records of 13 dogs with suspected scrotal contact dermatitis were retrospectively included in the study. For each case, historical findings, results of physical and dermatological examination and of avoidance tests as well as follow-up were included. Results of re-exposure tests and patch tests were also included when available. RESULTS: Avoidance tests to various suspected substances such as floor detergents, bleach, cement, laundry detergent and plastic fabric were performed and led to clinical improvement in all patients. Provocative re-exposure was performed in six cases, with five positive responses. Patch tests were undertaken in three of the five re-exposed cases, with two responding positively. CLINICAL SIGNIFICANCE: Scrotal skin is thin and with few hair follicles, and is therefore very susceptible to contact dermatitis. A range of substances can induce contact dermatitis. The diagnosis of contact dermatitis is made by results of avoidance and/or provocation tests and/or patch tests. Once an aetiological agent has been identified, treatment is straightforward consisting of avoidance of this agent.

Dermatophagoides farinae-specific immunotherapy in atopic dogs with hypersensitivity to multiple allergens: a randomised, double blind, placebo-controlled study.

A randomised, placebo-controlled, double blind study was conducted on 25 dogs that had atopic dermatitis, together with skin test reactivity and elevated serum IgE to Dermatophagoides farinae (Df) and at least one additional allergen. Dogs were treated with either a Df-restricted immunotherapy solution (n=14) or a placebo (n=11) and evaluated 6 weeks and 3, 5, 7 and 9 months after the initiation of treatment using a clinical scoring system (SASSAD) and pruritus analogue scale scores. The Df-restricted solution and the placebo had an equal effect on both pruritus and the skin manifestations (P>0.05). The results of this study indicate that in dogs with atopic dermatitis based on hypersensitivity to environmental allergens in addition to D. farinae, Df-restricted immunotherapy is insufficient to control the disease. Consequently, a solution for allergen-specific immunotherapy should remain customised.

Detection of a novel papillomavirus in pigmented plaques of four pugs.

Pugs are predisposed to the development of deeply pigmented, slightly elevated hyperkeratotic noncancerous plaques. Polymerase chain reaction amplification of a papillomavirus (PV)-like DNA fragment from such lesions suggested that PV may be responsible for them, although the predicted virus has not yet been identified. The goal of the present study was to make use of pigmented plaques from four pugs to identify and sequence the predicted virus. Taking advantage of the circular nature of PV DNA, the entire viral genome was amplified by rolling circle amplification and restriction enzyme analysis disclosed the same pattern in all four cases. Sequencing of one of the amplificates revealed a novel canine PV, termed CPV4, related to the recently described CPV3 but clearly distinct from canine oral PV and CPV2. Thus, a novel canine PV and a method for its future diagnosis are described.

Localised sarcoptic mange in dogs: a retrospective study of 10 cases.

The authors report 10 cases of localised sarcoptic mange in dogs. In each case, lesions were localised to one precise area of the skin. Pruritus was present in nine cases and absent in one. Affected areas were the feet (one case), the face and/or the pinnae (six cases), the abdominal skin (one case), the flank (one case) and the lumbar area (one case). The types of lesions were erythema, papules, lichenification, scales, crusts and alopecia. Parasites were found in all cases except one, in which anti-immunoglobulin G Sarcoptes serology was positive. The acaricidal treatments given were lindane, ivermectin or selamectin and were all successful.

Prospective study of bacterial overgrowth syndrome in eight dogs.

Eight dogs with cutaneous lesions, clinical signs and cytological findings compatible with bacterial overgrowth syndrome were compared with four healthy dogs. The affected dogs were treated for 28 days with 30 mg/kg/day cephalexin. The results showed that the syndrome was a superficial cutaneous disorder characterised by marked pruritus, greasy seborrhoea, offensive odour, erythema, lichenification, hyperpigmentation, excoriations and alopecia involving principally the ventral aspect of the body, but no papules, pustules, epidermal collarettes or crusts; it was caused by overgrowths of Staphylococcus intermedius all over the body surface. Histopathological findings included a superficial, perivascular, hyperplastic and spongiotic dermatitis with a mixed inflammatory infiltrate, but no lesions suggestive of a true pyoderma. In the affected dogs, anti-staphylococcal immunoglobulin G levels were high, but anti-staphylococcal immunoglobulin E levels were low, suggesting that staphylococcal hypersensitivity is not the underlying pathogenic process. The antibiotic treatment improved the condition of all the dogs, but five of the eight had an underlying allergic skin disease.

Therapy of difficult cases of canine pyoderma with marbofloxacin: a report of 39 dogs.

Thirty-nine dogs with severe and/or recurrent lesions of pyoderma were treated with marbofloxacin at an average dosage of 2.12 mg/kg bodyweight, once daily, for time periods varing from 10 to 213 days. Forty-seven strains of bacteria, isolated from 34 cultures, were tested for sensitivity to various antibiotics. At day 0, no resistance to marbofloxacin was found, but one refractory case, a strain of Staphylococcus intermedius resistant to marbofloxacin, was cultured at day 28. Thirty-three dogs (84.6 per cent) showed an excellent response (cure), one (2.6 per cent) a clear improvement and one (2.6 per cent) a smaller improvement, while the remaining four dogs showed no response after 11 to 60 days. Fifteen dogs (45.5 per cent) relapsed over the follow-up period of three to 191 days, but none of the dogs in the study exhibited any adverse effects.

Morphea-like lesion in a cat.

Scleroderma is a rare chronic disease of connective tissues, involving the skin and/or internal organs in humans, and rarely described in the dog. A case is reported of localised scleroderma in a cat which presented with two well delineated alopecic, sclerotic, raised and shiny lesions localised on the trunk. Diagnosis was made by histopathological examination of skin biopsies which showed the replacement of all dermal components by dense thick collagen bundles. No therapy was instituted and a spontaneous recovery occurred three months later. Clinical and histopathological aspects of this feline dermatosis are compared with human and canine morphea.

Treatment of canine pyoderma with co-amoxyclav: a comparison of two dose rates.

The efficacy of oral co-amoxyclav, administered twice daily for up to 12 weeks either at the manufacturer's dose rate of 12.5 mg/kg or at 25.0 mg/kg, in curing the lesions of canine folliculitis, furunculosis and cellulitis was compared in a blind study. A total of 97 dogs entered the trial and 67 completed it. There was no significant difference in the rate of cure or the duration of therapy. The lesions of folliculitis were cured in 91.5 per cent of cases, in a mean period of 25.3 days. Furunculosis and cellulitis were cured respectively in 87.5 per cent and 60.0 per cent of the dogs, in mean periods of 37.6 and 44.7 days. The standard dose rate was very effective in folliculitis and furunculosis and there was no benefit in doubling the dose. Too few cases of cellulitis were treated to provide a reliable dose comparison.

Orf and pregnancy.

A 31-year-old woman presented with orf on the forefingers at 34 weeks of gestation. The disease, contracted after handling sheep a week before, was uncomplicated, and the patient gave birth at term to a normal baby. Although some cases with features suggestive of viremic spread had been described, the authors find an overall benign picture of orf in man and recommend symptomatic therapeutic measures.