Scene segmentation techniques for the analysis of routine bone marrow smears from acute lymphoblastic leukemia patients.

Automated analysis of lymphoblast cell morphology is being evaluated as a basis for predicting the response to therapy of patients with acute lymphoblastic leukemia. A new technique of scene segmentation particularly applicable to the "cluttered" images of cells in routine bone marrow smears is described. Morphologic characteristics of lymphoblasts found in bone marrow smears made at time of diagnosis were measured by an automated, interactive image-processing system using the new scene segmentation technique. These characteristics, on a patient by patient basis, are being compared to remission length and survival data to develop and test new prognostic methods.

Computer-aided medical decision making in radiotherapy.

Radiotherapy departments are becoming sophisticated in working with computers for isodose computations, treatment machine verifications and administrative and medical records. The next step lies in computer-assisted medical decision making. The logic for a patient's diagnostic work-up and treatment protocol can be stored in a computer. It can then be used as an aid in making the diagnosis, in prescribing the treatment and for quality control. For patients who fit established protocols the computer can select and list treatment using the logic of that protocol. Such a system has been implemented for the postoperative radiotherapy of breast cancer on a trial basis. Its potential usefulness is illustrated by results in 25 consecutive patients. Physician acceptance and costs of the program are under investigation.

The computer-assisted morphological classification of acute leukemia. I. Preliminary results.

The morphology of leukemic lymphoblasts, as seen in the initial routine bone marrow aspirate, of 40 children with ALL has been evaluated using a computer-assisted automated microscope. A statistic, derived from a combination of the number of macrolymphoblasts and the percentage of cells with no cytoplasm was found to predict response to standard therapy and to identify patients with a high probability of long-term remission as well as a group with a relatively poor response to therapy.

An automated microscope for cytologic research a preliminary evaluation.

A research-oriented system for automated microscopy is described from an operational point of view. The system consists of a microscope, a TV camera, an automatic cell finder and a servo-driven computer controlled stage. The system is interfaced to a NOVA 840 computer having 112,000 words of 16-bit core memory and extensive peripherals. It is capable of performing a wide variety of image processing tasks and is being used to study various aspects of automated microscopy, with applications in, but not limited to, cytology. Results of preliminary performance evaluations are given.