IoMT-Based Automated Detection and Classification of Leukemia Using Deep Learning.

For the last few years, computer-aided diagnosis (CAD) has been increasing rapidly. Numerous machine learning algorithms have been developed to identify different diseases, e.g., leukemia. Leukemia is a white blood cells- (WBC-) related illness affecting the bone marrow and/or blood. A quick, safe, and accurate early-stage diagnosis of leukemia plays a key role in curing and saving patients' lives. Based on developments, leukemia consists of two primary forms, i.e., acute and chronic leukemia. Each form can be subcategorized as myeloid and lymphoid. There are, therefore, four leukemia subtypes. Various approaches have been developed to identify leukemia with respect to its subtypes. However, in terms of effectiveness, learning process, and performance, these methods require improvements. This study provides an Internet of Medical Things- (IoMT-) based framework to enhance and provide a quick and safe identification of leukemia. In the proposed IoMT system, with the help of cloud computing, clinical gadgets are linked to network resources. The system allows real-time coordination for testing, diagnosis, and treatment of leukemia among patients and healthcare professionals, which may save both time and efforts of patients and clinicians. Moreover, the presented framework is also helpful for resolving the problems of patients with critical condition in pandemics such as COVID-19. The methods used for the identification of leukemia subtypes in the suggested framework are Dense Convolutional Neural Network (DenseNet-121) and Residual Convolutional Neural Network (ResNet-34). Two publicly available datasets for leukemia, i.e., ALL-IDB and ASH image bank, are used in this study. The results demonstrated that the suggested models supersede the other well-known machine learning algorithms used for healthy-versus-leukemia-subtypes identification.

Acute lymphoblastic leukemia and chronic lymphocytic leukemia in dogs / 동물의과학연구지

An Australian cattle dog (case 1: 6-year-old castrated male) and a Shih-Tzu dog (case 2: 8-year-old castrated male) were referred to the Gyeongsang Animal Medical Center due to anorexia and depression. Physical examinations, complete blood counts, serum chemical analysis, radiography, ultrasonography, and bone marrow biopsy were performed. Upon physical examinations of cases 1 and 2, enlargement of superficial lymph nodes was not identified. Hematologic findings in these dogs included leukocytosis with severe lymphocytosis, anemia, and thrombocytopenia. Upon radiography, both dogs showed splenomegaly. Upon examination of a peripheral blood smear in case 1, immature lymphoid cells, featuring decreased nuclear chromatin condensation and nuclear pleomorphism, were present. Biopsy samples of the bone marrow in case 1 revealed hypercellularity as well as a large number of immature lymphoblastic cells similar in shape to cells in the peripheral blood. The characteristic morphological features of peripheral blood and bone marrow samples in case 2 were small lymphocytes. Thus, the dogs were tentatively diagnosed with acute lymphoblastic leukemia (ALL) and chronic lymphocytic leukemia (CLL), respectively. After diagnosis, the CLL patient was administered chlorambucil and prednisolone therapy. Due to its similarity to human leukemia, the canine leukemia model provides a valuable model for research into human leukemia.

Estimation of salivary amylase and total proteins in leukemia patients and its correlation with clinical feature and radiographic finding.

BACKGROUND: Leukemia is a fatal disease. The oral manifestations of the leukemias occur early in the course of the disease and these oral features can at times act as a diagnostic indicator. Saliva has been used as a diagnostic aid in a number of systemic diseases. MATERIALS AND METHODS: In our study, samples of unstimulated saliva of 30 leukemia patients who were not on chemotherapy were collected and analyzed for salivary amylase and total protein. The oral manifestations and radiographic changes (OPG) were recorded. The correlation between the oral manifestations and the salivary components (salivary amylase and total protein) was assessed for prognostic significance. RESULTS: In the present study when the mean values of salivary amylase (1280±754 U/ml) and total protein (647.2±320.7 mg%) were compared with that in control subjects. There was a statistically significant difference for amylase levels (P<.05). On intraoral examination the study subjects showed pallor, gingivitis, gingival enlargement, petechiae, and ecchymosis. On the OPG, the radiographic features included generalized rarefaction of bone (20%), thinning of lamina dura (3.4%), generalized alveolar crest bone resorption (30%), thinning of walls of alveolar crypts (6.7%), besides others, e.g., periapical abscess (10%). CONCLUSIONS: The saliva of leukemic patients demonstrated obvious changes in composition. A rise in salivary amylase and total protein levels was evident, with the increase in amylase levels being statistically significant.

Myeloablative radioimmunotherapy with Re-188-anti-CD66-antibody for conditioning of high-risk leukemia patients prior to stem cell transplantation: biodistribution, biokinetics and immediate toxicities.

BACKGROUND: Stem cell transplantation (SCT) is potentially curative for high-risk leukemia patients. Conditioning regimens affect relapse rate and treatment-related mortality. We evaluated biodistribution, radiation absorbed organ doses and immediate toxicities of myeloablative radioimmunotherapy with marrow selective 188rhenium (188Re)-labeled anti-CD66 monoclonal antibody (mAb). METHODS: Fifty high-risk leukemia patients were treated 14 +/- 2 days prior to SCT. Dosimetric measurements were performed at 1.5, 3, 20, 26, and 44 hours after about 1 GBq of 188Re followed by radioimmunotherapy with about 10 GBq 188Re. Standard conditioning consisted of high-dose chemotherapy and 12 Gy total-body irradiation. Forty-six patients received allogenic, and four received autologous, stem cell grafts. RESULTS: The mean radiation absorbed doses (in Gy) were: marrow, 13.9 +/- 4.6; liver, 5.7 +/- 2.7; spleen, 22.6 +/- 25.5; kidneys, 6.8 +/- 2.6; lungs, 0.8 +/- 0.7; total body, 1.4 +/- 0.3. The tumor-to-organ-ratios were 2.4 for liver, 0.6 for the spleen, 2.0 for the kidneys and 17.8 for the lungs. Type of leukemia did not affect radiation absorbed doses of marrow, lungs, kidneys and liver. Mean marrow dose of transplanted patients in complete remission was 1.37 +/- 0.43 Gy/GBq, compared with 1.34 +/- 0.29 Gy/GBq for patients with leukemic blast marrow infiltration of 5-25%. Immediate side effects were moderate. All patients showed primary engraftment. After a median follow-up of 11.0 +/- 7.4 months 28/50 patients (56%) are in ongoing complete remission. Nine patients (5%) have relapsed, seven (4%) of them have died. Another 13 patients (7%) died of treatment-related causes. CONCLUSIONS: Due to its biodistribution, radiation absorbed organ doses, low toxicity and clinical data, myeloablative radioimmunotherapy with 188Re-labeled anti-CD66 mAb seems to be a promising method for improving standard conditioning of high-risk leukemia patients prior to SCT.

CT findings in hepatosplenic and renal candidiasis.

Fourteen patients with the diagnosis of leukemia and one with lymphoma developed systemic candidiasis. Involvement of the liver (15 patients), spleen (nine patients), and kidney (five patients) was diagnosed by clinical, CT, and pathologic findings. The CT findings ranged from low-density lesions (11 livers, nine spleens, and five kidneys) to hepatomegaly or hepatosplenomegaly. All livers and three kidneys had positive biopsy findings for Candida. Two patients with diffuse splenic lesions underwent splenectomy and were proven to have candidiasis. During a 1 year follow-up, two patients developed hepatic calcifications and one developed renal calcifications. In proper clinical setting, CT should be done for simultaneous evaluation of the liver, spleen, and kidneys. These studies, when positive, are useful to guide percutaneous or open biopsy and to follow the results of therapy. However, regardless of the hepatic CT finding, biopsy should be obtained to establish the diagnosis and begin proper treatment.

Lung cancer in chronic leukemia and lymphoma.

Review of the number of lung cancers subsequently developing in patients with chronic leukemia or lymphoma revealed a statistically significant (p less than .001) increase in the incidence of lung cancer in these patients. Of 684 patients with chronic leukemia seen between 1961 and 1972 (followed through 1976), 19 developed lung cancer versus 3 expected cases. Of 2708 patients with lymphoma seen in the same period, 23 developed lung cancer versus 7 expected cases. These data indicate that lung cancer be given serious consideration when a new pulmonary lesion is noted in these patients, and biopsy may be warranted.